about 3 hours ago
Toronto, Canada
Mid Level / Senior / Staff+
H1B Sponsor
Responsibilities
- Lead the evolution of ElasticGPT into a task-oriented agent.
- Design sophisticated workflows using frameworks like LangGraph and LangChain.
- Architect hybrid retrieval systems to improve answer quality.
- Oversee the full model lifecycle from fine-tuning to deployment on Kubernetes.
- Manage token efficiency, latency, and cost for optimal performance.
- Design LLM gateway architectures for multi-model orchestration.
- Ensure governance and reliability in agent execution.
Requirements
- Proven experience in building production-grade agents and RAG systems.
- Mastery of Python and TypeScript, with experience in PyTorch or TensorFlow.
- Deep knowledge of Elasticsearch and vector indexing.
- Strong system design intuition balancing latency, cost, and response quality.
- Extensive experience with Kubernetes and cloud infrastructure.
- Ability to translate complex business needs into technical roadmaps.
- Bachelor's or Master's degree in Computer Science or related field.
Benefits
- Competitive pay based on the work you do.
- Health coverage for you and your family.
- Flexible locations and schedules.
- Generous vacation days each year.
- Financial matching for donations and service.
- Up to 40 hours for volunteer projects.
- Minimum of 16 weeks of parental leave.
Categories
AI & MLData EngineeringDevOps